Berkeley's SkyDiscover-Synthesize: AI generating just-in-time software for any workload
CShorten30 · x · 2026-10-06
Weaviate Podcast #147 features Shu Liu, Shubham Agarwal, Mert Cemri, and Alexander Krentsel from UC Berkeley's Sky Computing Lab on SkyDiscover-Synthesize.
The research explores "just-in-time systems": AI generating tailored software on the fly—from task queues and databases to inference engines like vLLM—eliminating the "generality tax" of one-size-fits-all software.
The episode also covers how Claude Code and AI coding tools are changing what software even is.
Related event: UC Berkeley's SkyDiscover: AI Generates Specialized Software On Demand(4 posts)→
More from coding & agent
- Same model, very different performance: Dylan Patel on why the harness matters — MatthewBerman · 2026-10-08
- EreNodes after a year and 44 versions: prompts as clickable pills in ComfyUI — Erehr · 2026-10-08
- localmcplib: an open-source shared component library for local MCP servers — mostly_deterministic · 2026-10-08
- e2e: open-source agent turns natural-language goals into E2E tests for web and mobile — abhishek__AI · 2026-10-08
- TERMy24k: billed as the first local neuro-symbolic AI terminal assistant — gioscarab · 2026-10-08
- Managed Agents on Interactions API: one call spins up Antigravity agents in a remote sandbox — clmt · 2026-10-08